weekly-ops-review

v1.0.0

Turn scattered notes, metrics, and unfinished tasks into a weekly operating review with wins, misses, blockers, and next-week priorities.

0· 177·0 current·0 all-time
byvx:17605205782@52yuanchangxing
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
Name/description ask for turning notes/metrics/tasks into a weekly review. Declared requirement is only python3 and the included files (script + template) directly support that. No unrelated credentials, binaries, or config paths are requested.
Instruction Scope
SKILL.md instructs summarization, using the bundled script and resource file. It explicitly limits actions (preview first, don't fabricate metrics) and references only local files. There are no instructions to read unrelated system files, fetch remote endpoints, or exfiltrate data.
Install Mechanism
No install spec — instruction-only skill. The only code is a small local Python helper (scripts/weekly_review_pack.py) which is clear, auditable, and writes a simple JSON file. No remote downloads, package installs, or extracted archives.
Credentials
No environment variables, credentials, or config paths are required. The single declared runtime dependency (python3) is proportional and expected for the included script.
Persistence & Privilege
always is false and the skill does not request elevated system privileges or modify other skills. The helper script writes a user-specified output file but does not alter global agent config. The skill can be invoked autonomously by the agent (default), which is normal; this alone is not a security concern.
Assessment
This skill appears safe and coherent. If you plan to use it: (1) inspect the local script (scripts/weekly_review_pack.py) yourself — it simply writes a JSON skeleton; (2) avoid providing secrets or sensitive credentials as notes/metrics inputs (the skill has no declared safeguards); (3) when asked to write files, confirm the output path to avoid accidental overwrite; and (4) if you need stricter guarantees, run the script in a sandbox or review outputs before committing them to other systems.

Like a lobster shell, security has layers — review code before you run it.

latestvk977zfazf0jv2ybkfc340gnb2582vyf3

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

Runtime requirements

🧰 Clawdis
Binspython3

Comments